Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to assembly and modular components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Things consisting of parts or components

    np_acts-logits-general · gemini-2.0-flash

    parts and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    autaire
    -0.67
    脚注の使い方
    -0.66
    windowFixed
    -0.66
     coals
    -0.65
    addCriterion
    -0.65
     automatiques
    -0.65
    NewLabel
    -0.64
    IsMutable
    -0.63
    collants
    -0.61
     laſt
    -0.61
    POSITIVE LOGITS
     components
    1.02
     parts
    0.97
    parts
    0.83
    components
    0.81
    Parts
    0.81
     Parts
    0.79
     Components
    0.78
     componenti
    0.74
     component
    0.74
     PARTS
    0.72
    Act Density 0.393%

    No Known Activations